GPT-4 Turbo
OpenAI · Compact GPT model for low-latency assistance and high-volume workloads
Key facts
- Provider
- OpenAI
- Context window
- 128K tokens
- Max output
- 4.1K tokens
- Input price
- $10 / M tok
- Output price
- $30 / M tok
- Knowledge cutoff
- Dec 2023
- Released
- Nov 6, 2023
- License
- —
Capabilities
ReasoningTool callingStructured outputFile attachmentsTemperature controlOpen weights
Pricing
USD per million tokens, list API rates.
- Input
- $10
- Output
- $30
- Cache read
- —
- Cache write
- —
Modalities
- Input
- Text, Image
- Output
- Text